© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 21730
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "fashionista."

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of artistic expression or creators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EY
    -0.67
     Ring
    -0.65
     spare
    -0.59
     Irving
    -0.59
    fill
    -0.59
     flesh
    -0.59
     Gray
    -0.58
     chrom
    -0.58
     separate
    -0.58
     bonding
    -0.56
    POSITIVE LOGITS
    ista
    4.92
    istas
    3.72
    ismo
    1.91
    iste
    1.68
    ist
    1.45
    ists
    1.30
    istically
    1.20
    istic
    1.18
    istics
    1.15
    isma
    1.10
    Activations Density 0.016%

    No Known Activations